Hybrid Autoencoder for Interference Detection in Raw GNSS Observations

Malfunctions or failures in Global Navigation Satellite System (GNSS) services can result in significant personal, material, and financial damages. By an early identification of anomalous behavior in GNSS signals, timely countermeasures can be taken. However, most of interference monitoring or mitigation techniques are only applicable with the use of high-end receivers and require a certain level of knowledge to be used effectively. This paper presents a GNSS interference monitoring approach employing machine learning methodologies that can be utilized by users of any expertise level and with any type of GNSS receiver capable of outputting raw GNSS observations. By leveraging simple signal-to-noise ratio (SNR) observations, different hybrid autoencoder models, including denoising or variational autoencoder combined with recurrent neural network (RNN) models, are trained and tested on real jamming and spoofing events. The developed monitoring system is represented by a “traffic-lights” system, indicating the severity or level of concern associated with each detected anomaly. The results contain a comparison between different RNN-based autoencoder implementations and have been tested on input data from high-end to low-end GNSS receivers. The analysis of the test set showed that there is a 95% probability of catching anomalies. Additionally, when applied to other geodetic receiver types like u-blox or Javad GNSS receivers, similar results were achieved. However, smartphone data is subject to some limitations. Notably, missed anomalies are primarily attributed to the low transmitting power from the jamming and spoofing devices, which poses challenges for detection.